Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Dev tools
16,833 results · page 89 of 562
- View details
thinking-probabilisticSkillDev tools
Use when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into order-of-magnitude bounds.
Ready to connect★ 1k
- View details
thinking-reversibilitySkillDev tools
Before heavy deliberation, classify the decision as cheap or costly to undo; decide two-way doors fast and stage one-way doors to preserve options.
Ready to connect★ 1k
- View details
thinking-scientific-methodSkillDev tools
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
Ready to connect★ 1k
- View details
thinking-second-orderSkillDev tools
When a change has effects past the immediate fix—incentives, scale, feedback—trace consequence chains with timing and probability before committing.
Ready to connect★ 1k
- View details
thinking-socraticSkillDev tools
When a request is vague, assumption-laden, or "obvious," ask the few load-bearing questions that expose hidden requirements before building or committing.
Ready to connect★ 1k
- View details
thinking-steel-manningSkillDev tools
Before rejecting a proposal or reflexively agreeing, build the strongest faithful opposing case, state agreement conditions, then update or reaffirm.
Ready to connect★ 1k
- View details
thinking-systemsSkillDev tools
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
Ready to connect★ 1k
- View details
thinking-theory-of-constraintsSkillDev tools
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
Ready to connect★ 1k
- View details
thinking-thought-experimentSkillDev tools
When a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate one variable, fix conditions, trace the mechanistic chain, and bound what the result implies.
Ready to connect★ 1k
- View details
thinking-via-negativaSkillDev tools
Use when the reflex is to add a feature, layer, or process. Prefer removing harmful or nonessential elements first, with an irreversibility guard before deletion.
Ready to connect★ 1k
- View details
creating-toolsSkillDev tools
Scaffold and build new tool integrations in tools/. Use when asked to create a new tool, add an API integration, or build a new client for an external service.
Ready to connect★ 1k
- View details
dogfoodSkillDev tools
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduct
Ready to connect★ 1k
- View details
helpersSkillDev tools
Provides JavaScript/TypeScript helper functions and utilities for SonarJS rule implementation. Use when implementing rule fixes, searching for existing utilities, or needing to check available helper functions.
Ready to connect★ 1k
- View details
rule-optionsSkillDev tools
Add or modify rule options in SonarJS, including the fields array, SonarQube UI visibility, and Java check class configuration. Use when working on rule configurations.
Ready to connect★ 1k
- View details
rulingSkillDev tools
Run ruling integration tests and update expected results for SonarJS rules. Use when running ruling tests or syncing expected ruling output.
Ready to connect★ 1k
- View details
sonar-docsSkillDev tools
SonarSource Static Analyzer for JavaScript and TypeScript
Ready to connect★ 1k
- View details
test-quality-standardsSkillDev tools
Provides test quality standards and best practices. Use when writing test cases, creating unit tests, implementing tests, or refining/reviewing test code. Essential for test generation and test refinement phases.
Ready to connect★ 1k
- View details
test-ruleSkillDev tools
Write and run tests for a SonarJS rule. Use when working on rule tests, writing test fixtures, or running unit tests for a specific rule.
Ready to connect★ 1k
- View details
gbro-collage-brollSkillDev tools
Turns roughly 5 seconds of voiceover script, a viewpoint sentence, or an abstract concept into premium editorial halftone paper-collage B-roll. Use this skill whenever the user says "collage b-roll", "paper collage b-roll", "halftone collage", "collage-style visuals", "make a collage animation from
Ready to connect★ 1k
- View details
seo-growthSkillDev tools
Use when deciding WHERE to point SEO effort, not how to write a page. Triggers: a new site or brand with no rankings and no authority ("cold start", "starting from zero", "nobody knows us"), deciding what to double down on, a page or cluster that ranks but earns nothing, hunting emerging or newly-co
Ready to connect★ 1k
- View details
cutedsl-tunable-kernel-templateSkillDev tools
Adds an Attention Gym tuning adapter to a CuTeDSL op using typed input-aware configs, cached fake-tensor TVM-FFI compilation, parallel candidate compilation, and sequential GPU benchmarking. Use after the core kernel exists and needs a public default, explicit-config, or autotune path.
Ready to connect★ 1k
- View details
validating-pytorch-custom-opsSkillDev tools
Ensures new Attention Gym eager, Triton, CuTeDSL, and external-library implementations are torch.compile-friendly and correctly registered. Use when adding or reviewing an implementation or custom kernel; covers custom_op, triton_op, fake tensors, autograd, opcheck, full-graph compilation, dynamic s
Ready to connect★ 1k
- View details
worktree-env-setupSkillDev tools
Sets up an isolated per-worktree Python environment for attention-gym development using nightly PyTorch and the CI-mirroring uv flow. Use when creating a new git worktree or when a worktree lacks a local .venv.
Ready to connect★ 1k
- View details
add-lua-binding-apiSkillDev tools
Add Cataclysm-BN Lua API bindings for global game functions, utility libraries, constants, callbacks, and domain-specific Lua namespaces.
Ready to connect★ 1k
- View details
add-lua-binding-complexSkillDev tools
Add comprehensive Cataclysm-BN Lua bindings for complex C++ classes with methods, inheritance, constructors, properties, operators, and ownership rules.
Ready to connect★ 1k
- View details
add-lua-binding-simpleSkillDev tools
Add simple Cataclysm-BN Lua bindings for string_id types, enums, and basic read-only C++ types. Use when exposing straightforward C++ types to Lua.
Ready to connect★ 1k
- View details
changelog-genSkillDev tools
Rewrite every `docs/*/game/changelog/{order}.stable-{semver}.md` from a ref range. Default `--limit=20`.
Ready to connect★ 1k
- View details
deno-scriptSkillDev tools
Write or modify Cataclysm-BN Deno/TypeScript scripts. Use for scripts, tools, migrations, generators, git hooks, and CLI utilities.
Ready to connect★ 1k
- View details
i18n-contextSkillDev tools
Add gettext context for ambiguous user-facing strings and repair affected PO translations.
Ready to connect★ 1k
- View details
release-genSkillDev tools
Finish release follow-up after the changelog exists. Update `data/XDG/org.cataclysmbn.CataclysmBN.metainfo.xml` and send the matching Flathub PR with `gh pr create --web`.
Ready to connect★ 1k
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,585 of the 54,017 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.